
pip install plotly

Requirement already satisfied: plotly in /opt/conda/lib/python3.9/site-packages (5.19.0)
Requirement already satisfied: tenacity>=6.2.0 in /opt/conda/lib/python3.9/site-packages (from plotly) (8.2.3)
Requirement already satisfied: packaging in /opt/conda/lib/python3.9/site-packages (from plotly) (23.1)
Note: you may need to restart the kernel to use updated packages.


#Let's import a Plotly package now to get started 
import plotly.express as px
import plotly as plotly
plotly.offline.init_notebook_mode()


#Using pandas, import Spotify data as a dataframe
import pandas as pd

data = pd.read_csv('spotify-2023.csv')


#And now a call to preview what we're working with
data.head()


def cleaning(df):
    
    #Change the value of streams to a number
    df['streams'] = pd.to_numeric(df['streams'], errors='coerce')
    
    #Rename date columns and sort the songs by the date they were released
    df = df.rename(columns={"released_year": "year", "released_month": "month", "released_day": "day" })
    df = df.sort_values(by=['year', 'month', 'day'], ascending=True)
    
        
    #Get rid of any NaN values
    df = df.dropna()
    
    return df

data = cleaning(data)

data.head()


def histogram(df):
    
    #Use px.histogram to plot the histogram 
    fig = px.histogram(df, 
                       x="key", 
                       color="mode",  #use color to create layered histograms
                       hover_data=df.columns  #add hover labels to bars 
                      )
    
    #Update titles and formatting
    fig.update_layout(title={'text': "Most Popular Song Keys of 2023",
                            'xanchor': 'center',
                            'yanchor': 'top',
                            'y':0.9,
                            'x':0.5
                            }, 
                      xaxis_title="Key",
                      yaxis_title="Number of Songs"
                     )
    return fig

histogram(data)


def curve_and_rug(df):

    #to plot a layered distribution, we will need to import figure factory first
    import plotly.figure_factory as ff
    
    #figure factory's distribution plot requires that we include histogram data as a list of lists
    hist_data = [df['danceability_%'], df['energy_%'],df['valence_%'], df['liveness_%'], df['acousticness_%'], df['speechiness_%']]
    
    #we will also need to give a label to each of these lists
    group_labels = ['Danceability %', 'Energy %', 'Valence %', 'Liveness %', 'Acousticness %', 'Speechiness %']
    
    #now we will plot the distrbution and set show_hist to 'False' to remove the bars
    fig = ff.create_distplot(hist_data, group_labels, show_hist=False )
    
    #Update titles and formatting
    fig.update_layout(title={'text': "Distribution of Popular Song Attributes in 2023",
                            'xanchor': 'center',
                            'yanchor': 'top',
                            'y':0.9,
                            'x':0.5
                            })
    return fig

curve_and_rug(data)


def scatter(df):
    
    #Plot a scatter plot using px.scatter
    fig = px.scatter(df, 
                     x='danceability_%', 
                     y="bpm", 
                     hover_name="track_name", #set the hover values to show names of tracks
                     size="streams",  #set the point size to vary by amount of streams
                     color="key",    #set the color of points to vary by categorical data key
                     trendline="ols",  #add an ordinary least squares regression line 
                     trendline_scope="overall",   #set trendline scope to overall to avoid having a trendline for each key
                    )
    
    #Update titles and formatting
    fig.update_layout(title={'text': "2023 Popular Song BPM to Danceability",
                            'xanchor': 'center',
                            'yanchor': 'top',
                            'y':0.9,
                            'x':0.5},
                      xaxis_title="Danceability %",
                      yaxis_title="Beats Per Minute"
                     )
    return fig

scatter(data)


def scatter_interactivity(df):
    
    #Again, plot using px.scatter
    fig = px.scatter(df, 
                     x='danceability_%', 
                     y="bpm", 
                     hover_name="track_name", 
                     size="streams",
                     color="key", 
                     trendline="ols", #This time we will use ordinary least squares regression without setting the trendline to "overall" since we are cycling through the keys
                     animation_frame="key", #setting the animation frame will create a slider for interactivty and set it to key to cycle through them
                    )
    
    #Update titles and formatting
    fig.update_layout(title={'text': "2023 Popular Song BPM to Danceability by Key",
                            'xanchor': 'center',
                            'yanchor': 'top',
                            'y':0.9,
                            'x':0.5},
                      xaxis_title="Danceability %",
                      yaxis_title="Beats Per Minute"
                     )
    return fig

scatter_interactivity(data)

	track_name	artist(s)_name	artist_count	released_year	released_month	released_day	in_spotify_playlists	in_spotify_charts	streams	in_apple_playlists	...	bpm	key	mode	danceability_%	valence_%	energy_%	acousticness_%	instrumentalness_%	liveness_%	speechiness_%
0	Seven (feat. Latto) (Explicit Ver.)	Latto, Jung Kook	2	2023	7	14	553	147	141381703	43	...	125	B	Major	80	89	83	31	0	8	4
1	LALA	Myke Towers	1	2023	3	23	1474	48	133716286	48	...	92	C#	Major	71	61	74	7	0	10	4
2	vampire	Olivia Rodrigo	1	2023	6	30	1397	113	140003974	94	...	138	F	Major	51	32	53	17	0	31	6
3	Cruel Summer	Taylor Swift	1	2019	8	23	7858	100	800840817	116	...	170	A	Major	55	58	72	11	0	11	15
4	WHERE SHE GOES	Bad Bunny	1	2023	5	18	3133	50	303236322	84	...	144	A	Minor	65	23	80	14	63	11	6

	track_name	artist(s)_name	artist_count	year	month	day	in_spotify_playlists	streams	in_apple_playlists	...	bpm	key	mode	danceability_%	valence_%	energy_%	acousticness_%	instrumentalness_%	liveness_%	speechiness_%
439	Agudo MÔøΩÔøΩgi	Styrx, utku INC, Thezth	3	1930	1	1	323	90598517.0	4	...	130	F#	Minor	65	49	80	22	4	7	5
469	White Christmas	Bing Crosby, John Scott Trotter & His Orchestr...	3	1942	1	1	11940	395591396.0	73	...	96	A	Major	23	19	25	91	0	40	3
460	The Christmas Song (Merry Christmas To You) - ...	Nat King Cole	1	1946	11	1	11500	389771964.0	140	...	139	C#	Major	36	22	15	84	0	11	4
466	Let It Snow! Let It Snow! Let It Snow!	Frank Sinatra, B. Swanson Quartet	2	1950	1	1	10585	473248298.0	126	...	143	D	Major	60	86	32	88	0	34	6
496	Jingle Bells - Remastered 1999	Frank Sinatra	1	1957	1	1	4326	178660459.0	32	...	175	G#	Major	51	94	34	73	0	10	5

Assignment 3 - Plotly Demo¶

Visualization Technique (25%)¶

Visualizations used:¶

How they work:¶

Circumstances in which this visualization should and should not be used:¶

Visualization Library (25%)¶

Plotly Overview¶

The general approach and limitations of Plotly¶

Demonstration (50%)¶

The dataset:¶

Instructions for cleaning:¶

Plotting a Histogram:¶

Creating a Curve and Rug Plot:¶

Creating a Scatter Plot:¶

Creating a Scatter Plot with Interactivity:¶